Long Short-Term Memory-Based Deep Learning Models for Screening Parkinson’s Disease Using Sequential Diagnostic Codes
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Background and Purpose It is challenging to detect Parkinson’s disease (PD) in its early stages, which has prompted researchers to develop techniques based on machine learning methods for detecting PD. However, previous studies did not fully incorporate the slow progression of PD over a long period of time nor consider that its symptoms occur in a time-sequential manner. Contributing to the literature on PD, which has relied heavily on cross-sectional data, this study aimed to develop a method for detecting PD early that can process time-series information using the long short-term memory (LSTM) algorithm. Methods We sampled 926 patients with PD and 9,260 subjects without PD using medicalclaims data. The LSTM algorithm was tested using diagnostic histories, which contained the diagnostic codes and their respective time information. We compared the prediction power of the 12-month diagnostic codes under two different settings over the 4 years prior to the first PD diagnosis. Results The model that was trained using the most-recent 12-month diagnostic codes had the best performance, with an accuracy of 94.25%, a sensitivity of 82.91%, and a specificity of 95.26%. The other three models (12-month codes from 2, 3, and 4 years prior) were found to have comparable performances, with accuracies of 92.27%, 91.86%, and 91.81%, respectively. The areas under the curve from our data settings ranged from 0.839 to 0.923. Conclusions We explored the possibility that PD specialists could benefit from our proposed machine learning method as an early detection method for PD.
Abstract
Background and Purpose It is challenging to detect Parkinson’s disease (PD) in its early stages, which has prompted researchers to develop techniques based on machine learning methods for detecting PD. However, previous studies did not fully incorporate the slow progression of PD over a long period of time nor consider that its symptoms occur in a time-sequential manner. Contributing to the literature on PD, which has relied heavily on cross-sectional data, this study aimed to develop a method for detecting PD early that can process time-series information using the long short-term memory (LSTM) algorithm. Methods We sampled 926 patients with PD and 9,260 subjects without PD using medicalclaims data. The LSTM algorithm was tested using diagnostic histories, which contained the diagnostic codes and their respective time information. We compared the prediction power of the 12-month diagnostic codes under two different settings over the 4 years prior to the first PD diagnosis. Results The model that was trained using the most-recent 12-month diagnostic codes had the best performance, with an accuracy of 94.25%, a sensitivity of 82.91%, and a specificity of 95.26%. The other three models (12-month codes from 2, 3, and 4 years prior) were found to have comparable performances, with accuracies of 92.27%, 91.86%, and 91.81%, respectively. The areas under the curve from our data settings ranged from 0.839 to 0.923. Conclusions We explored the possibility that PD specialists could benefit from our proposed machine learning method as an early detection method for PD.
참고문헌 (39)
- Kalia LV, "Parkinson’s disease", Lancet, 386, pp.896~912 (2015)
- Postuma RB, "Advances in markers of prodromal Parkinson disease", Nat Rev Neurol, 12, pp.622~634 (2016)
- Postuma RB, "MDS clinical diagnostic criteria for Parkinson’s disease", Mov Disord, 30, pp.1591~1601 (2015)
- Tolosa E, "Challenges in the diagnosis of Parkinson’s disease", Lancet Neurol, 20, pp.385~397 (2021)
- Almeida JS, "Detecting Parkinson’s disease with sustained phonation and speech signals using machine learning techniques", Pattern Recognit Lett, 125, pp.55~62 (2019)
- Karapinar Senturk Z, "Early diagnosis of Parkinson’s disease using machine learning algorithms", Med Hypotheses, 138, pp.109603~ (2020)
- Lahmiri S, "Detection of Parkinson’s disease based on voice patterns ranking and optimized support vector machine", Biomed Signal Process Control, 49, pp.427~433 (2019)
- Parisi L, "Feature-driven machine learning to improve early diagnosis of Parkinson’s disease", Expert Syst Appl, 110, pp.182~190 (2018)
- Valenza G, "Assessment of spontaneous cardiovascular oscillations in Parkinson’s disease", Biomed Signal Process Control, 26, pp.80~89 (2016)
- Silveira-Moriyama L, "The use of a color coded probability scale to interpret smell tests in suspected parkinsonism", Mov Disord, 24, pp.1144~1153 (2009)
- Abdulhay E, "Gait and tremor investigation using machine learning techniques for the diagnosis of Parkinson disease", Future Gener Comput Syst, 83, pp.366~373 (2018)
- Cavallo F, "Upper limb motor pre-clinical assessment in Parkinson’s disease using machine learning", Parkinsonism Relat Disord, 63, pp.111~116 (2019)
- El Maachi I, "Deep 1D-convnet for accurate Parkinson disease detection and severity prediction from gait", Expert Syst Appl, 143, pp.113075~ (2020)
- Zeng W, "Parkinson’s disease classification using gait analysis via deterministic learning", Neurosci Lett, 633, pp.268~278 (2016)
- Prashanth R, "High-accuracy detection of early Parkinson’s disease through multimodal features and machine learning", Int J Med Inform, 90, pp.13~21 (2016)
- Wang W, "Early detection of Parkinson’s disease using deep learning and machine learning", IEEE Access, 8, pp.147635~147646 (2020)
- Chakraborty S, "Detection of Parkinson’s disease from 3T T1 weighted MRI scans using 3D convolutional neural network", Diagnostics(Basel), 10, pp.402~ (2020)
- Choi H, "Cognitive signature of brain FDG PET based on deep learning : domain transfer from Alzheimer’s disease to Parkinson’s disease", Eur J Nucl Med Mol Imaging, 47, pp.403~412 (2020)
- Shinde S, "Predictive markers for Parkinson’s disease using deep neural nets on neuromelanin sensitive MRI", Neuroimage Clin, 22, pp.101748~ (2019)
- Magesh PR, "An explainable machine learning model for early detection of Parkinson’s disease using LIME on DaTSCAN imagery", Comput Biol Med, 126, pp.104041~ (2020)
- Horsager J, "Brain-first versus body-first Parkinson’s disease : a multimodal imaging case-control study", Brain, 143, pp.3077~3088 (2020)
- Lee J, "Cohort profile : the national health insurance service–national sample cohort(NHIS-NSC), South Korea", Int J Epidemiol, 46, pp.e15~ (2017)
- Hochreiter S, "Long short-term memory", Neural Comput, 9, pp.1735~1780 (1997)
- Graves A, "Speech recognition with deep recurrent neural networks", Proceedings of the 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, pp.6645~6649 (2013), IEEE
- Malhotra P, "Long short term memory networks for anomaly detection in time series", Proceedings of the 23rd European Symposium on Artificial Neural Networks, pp.89~94 (2015), ESANN
- Tang D, "Document modeling with gated recurrent neural network for sentiment classification", Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp.1422~1432 (2015), EMNLP
- Lin TY, "Focal loss for dense object detection", IEEE Trans Pattern Anal Mach Intell, 42, pp.318~327 (2020)
- Kummer BR, "Associations between cerebrovascular risk factors and Parkinson disease", Ann Neurol, 86, pp.572~581 (2019)
- Huang YP, "Parkinson’s disease is related to an increased risk of ischemic stroke-a population-based propensity score-matched follow-up study", PLoS One, 8, pp.e68314~ (2013)
- Song IU, "Parkinson’s disease might increase the risk of cerebral ischemic lesions", Int J Med Sci, 14, pp.319~322 (2017)
- Lohmann S, "Ischemic stroke causes Parkinson’s disease-like pathology and symptoms in transgenic mice overexpressing alpha-synuclein", Acta Neuropathol Commun, 10, pp.26~ (2022)
- Postuma RB, "Identifying prodromal Parkinson’s disease : pre-motor disorders in Parkinson’s disease", Mov Disord, 27, pp.617~626 (2012)
- Choi E, "Doctor AI : predicting clinical events via recurrent neural networks", JMLR Workshop Conf Proc, 56, pp.301~318 (2016)
- Khalilia M, "Predicting disease risks from highly imbalanced data using random forest", BMC Med Inform Decis Mak, 11, pp.51~ (2011)
- Searles Nielsen S, "A predictive model to identify Parkinson disease from administrative claims data", Neurology, 89, pp.1448~1456 (2017)
- Fearon C, "The logic and pitfalls of Parkinson’s disease as"brain-first"versus"body-first"subtypes", Mov Disord, 36, pp.594~598 (2021)
- Kotsavasiloglou C, "Machine learning-based classification of simple drawing movements in Parkinson’s disease", Biomedical Signal Processing and Control, 31, pp.174~180 (2017)
- Gupta U, "An improved sex-specific and age-dependent classification model for Parkinson’s diagnosis using handwriting measurement", Computer Methods and Programs in Biomedicine, 189, pp.105305~ (2020)
- Arroyo-Gallego T, "Detection of motor impairment in Parkinson's disease via mobile touchscreen typing", IEEE Trans Biomed Eng, 64, pp.1994~2002 (2017)